search

paschalidoud / superquadric_parsing

Code for "Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids", CVPR 2019
https://superquadrics.com
Other
127 stars 32 forks source link

Very sparse voxels for input. #4

Open LR32768 opened 5 years ago

LR32768 commented 5 years ago

Hi I am very interested in your work and I'm trying to retrain the chair parsing network. But after following all the instructions as README and using same arguments, my converged model behaves much worse on Shapenet v2. The visualization for the input X (voxels) fed into model distribution is like this sparse while the ground truth mesh is like this Screenshot from 2019-09-02 15-28-13

Is this input sparsity intended or there is some version problem when releasing? I read the dataloader and find that such phenomenon comes from the occupancy grid voxelizer which only take mesh vertices into voxelize, is this as designed?

shubham-goel commented 4 years ago

I'm also facing this issue. Any update on this?